Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical ranges and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唪
    0.32
    كي
    0.30
     Bezug
    0.30
     Middleware
    0.29
    勍
    0.28
    IService
    0.27
     ObjectID
    0.27
    玾
    0.27
    愔
    0.27
    醀
    0.26
    POSITIVE LOGITS
    6
    0.73
    7
    0.68
    5
    0.64
    0.61
    8
    0.61
    4
    0.59
     seven
    0.56
    ６
    0.56
    ７
    0.56
    ５
    0.55
    Act Density 0.317%

    No Known Activations